Offline-Online Hierarchical 3D Global Relocalization With Synthetic LiDAR Sensing and Descriptor-Space Retrieval

Figure 1: Experimental UAV platform. A Livox MID360 LiDAR is mounted on top of the UAV for 3D perception, while an Intel NUC12 onboard computer handles real-time mapping and relocalization.

Figure 3: Constraint-aware uniform sampling in a 3D occupancy grid map.

Figure 4: Sampling on the 3D occupancy grid map with the same number of sampling steps: (a) 3D occupancy grid map; (b) standard 3D RRT sampling without the proposed constraints; (c) proposed constraint-aware RRT-based uniform sampling using the same number of samples as in (b).

Figure 2: Overall pipeline of the proposed LiDAR-based global 3D relocalization framework. The system takes as input a prior global point cloud map and real-time LiDAR scans. In the offline processing stage (orange), valid robot poses are uniformly sampled in the prior 3D occupancy grid map, a virtual LiDAR model is used to generate synthetic scans, and a descriptor database is constructed from the resulting virtual point clouds. In the online matching stage (blue), K_{f} consecutive LiDAR frames are accumulated to build a local grid map, a query descriptor is generated and matched against the

Figure 5: Pipeline of ray-casting-based scan synthesis and egocentric descriptor construction.

Figure 6: Two outdoor experimental scenarios and representative evaluation poses. (a) Wide corridor between buildings, approximately 120\,\mathrm{m}\times 50\,\mathrm{m} . (b) Uneven grassland/slope environment, approximately 150\,\mathrm{m}\times 80\,\mathrm{m} . The UAV flight trajectory is overlaid, and the numbered markers denote representative evaluation poses selected from typical regions (e.g., long corridors, cluttered areas, occluded areas, open spaces, T-junctions, and slopes). To emulate real-world disturbances, additional objects that are absent from the original map (e.g., bicycle

Figure 8: Qualitative comparison of Scan Context images produced by local-grid and global-map synthetic scans. (a) Scan Context generated from online accumulated LiDAR scans after voxelization into a local grid and sensor-centric first-return ray casting (no external pose input). (b) Scan Context generated by first-return ray casting on the global occupancy grid map at the relocalized position \hat{\mathbf{p}} . Both use N_{r}=20 rings and N_{s}=60 sectors with max-height encoding.